dc.contributor.author |
Luus, Francois Pierre Sarel
|
|
dc.contributor.author |
Salmon, Brian Paxton
|
|
dc.contributor.author |
Van den Bergh, Frans
|
|
dc.contributor.author |
Maharaj, Bodhaswar Tikanath Jugpershad
|
|
dc.date.accessioned |
2016-02-10T08:30:27Z |
|
dc.date.available |
2016-02-10T08:30:27Z |
|
dc.date.issued |
2015-12 |
|
dc.description.abstract |
A multiscale input strategy for multiview deep
learning is proposed for supervised multispectral land-use classification
and it is validated on a well-known dataset. The hypothesis
that simultaneous multiscale views can improve compositionbased
inference of classes containing size-varying objects compared
to single-scale multiview is investigated. The end-to-end
learning system learns a hierarchical feature representation with
the aid of convolutional layers to shift the burden of feature
determination from hand-engineering to a deep convolutional
neural network. This allows the classifier to obtain problemspecific
features that are optimal for minimizing the multinomial
logistic regression objective, as opposed to user-defined features
which trades optimality for generality. A heuristic approach to
the optimization of the deep convolutional neural network hyperparameters
is used, based on empirical performance evidence.
It is shown that a single deep convolutional neural network
can be trained simultaneously with multiscale views to improve
prediction accuracy over multiple single-scale views. Competitive
performance is achieved for the UC Merced dataset where
the 93.48% accuracy of multiview deep learning outperforms
the 85.37% accuracy of SIFT-based methods and the 90.26%
accuracy of unsupervised feature learning. |
en_ZA |
dc.description.librarian |
hb2015 |
en_ZA |
dc.description.sponsorship |
National Research Foundation (NRF) of South Africa |
en_ZA |
dc.description.uri |
http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=8859 |
en_ZA |
dc.identifier.citation |
Luus, FPS, Salmon, BP, Van Den Bergh, F & Maharaj, BTJ 2015, 'Multiview deep learning for land-use classification', IEEE Geoscience and Remote Sensing Letters, vol. 12, no. 12, pp. 2448-2452. |
en_ZA |
dc.identifier.issn |
1545-598X (print) |
|
dc.identifier.issn |
1558-0571 (online) |
|
dc.identifier.other |
10.1109/LGRS.2015.2483680 |
|
dc.identifier.uri |
http://hdl.handle.net/2263/51310 |
|
dc.language.iso |
en |
en_ZA |
dc.publisher |
Institute of Electrical and Electronics Engineers |
en_ZA |
dc.rights |
© 2015 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. |
en_ZA |
dc.subject |
Neural network applications |
en_ZA |
dc.subject |
Neural network architecture |
en_ZA |
dc.subject |
Feature extraction |
en_ZA |
dc.subject |
Urban areas |
en_ZA |
dc.subject |
Remote sensing |
en_ZA |
dc.title |
Multiview deep learning for land-use classification |
en_ZA |
dc.type |
Postprint Article |
en_ZA |